Synergies between cloud-fag-thing and brain-spinal cord-nerve networks

Date

2018-10-23

Author

Balevi, Eren
Gitlin, Richard D.

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

106
views

0
downloads

© 2018 IEEE.This paper is directed towards describing the striking similarities and synergies between cloud and fog nodes that constitute the cloud-Jog-thing [Fog Network] architecture proposed for 5G networks and the human brain-spinal cord-nerve network model. On the one hand, the central nervous system can be better modeled considering the duality with Fog Networks, and, on the other hand, novel algorithms/protocols inspired from the central nervous system can be developed for throughput and latency performance improvement in Fog Networks. Designing and managing large-scale Fog Networks using stochastic geometry and machine learning is applied to determine the optimum number of fog nodes and their locations that optimize throughput and latency for 5G networks. Having observed the close relation between the Fog Networks and the spinal cord, these results may be adapted to increase understanding of the role of spinal cord plasticity in learning and ultimately suggest new means of treating central nervous system disorders associated with the spinal cord plasticity. Inspired by the cooperation between the brain and the spinal cord, a modified coded caching policy is proposed for Fog Networks, that is, the files to be stored at the fog nodes are determined as a result of continuous information flow between cloud and fog nodes through the latent variables assigned to files.

Subject Keywords

Central nervous system, Fog networking, Machine learning, Spinal cord, Stochastic geometry

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85057265213&origin=inward
https://hdl.handle.net/11511/100352

DOI

https://doi.org/10.1109/ita.2018.8502957

Conference Name

2018 Information Theory and Applications Workshop, ITA 2018

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Unsupervised machine learning in 5G networks for low latency communications Balevi, Eren; Gitlin, Richard D. (2018-02-02) © 2017 IEEE.This paper incorporates fog networking into heterogeneous cellular networks that are composed of a high power node (HPN) and many low power nodes (LPNs). The locations of the fog nodes that are upgraded from LPNs are specified by modifying the unsupervised soft-clustering machine learning algorithm with the ultimate aim of reducing latency. The clusters are constructed accordingly so that the leader of each cluster becomes a fog node. The proposed approach significantly reduces the latency with ...
ACCLOUD (Accelerated CLOUD): A novel FPGA-Accelerated cloud archictecture-ACCLOUD: FPGA ile Hızlandırılmış Yeni bir BulutMimarisi YAZAR, ALPER; EROL, AHMET; Schmidt, Şenan Ece (2018-07-09) In this paper, we propose ACCLOUD (ACcelerated CLOUD) as a a novel architecture for cloud data centers. ACCLOUD features FPGA cards which work with the cloud servers or stand alone for hardware acceleration in the data plane. To this end, FPGA reconfigurable regions are virtualized and offered to the user together with other cloud resources including CPU, memory or disk. The cloud control is carried out within OpenStack framework incorporating the hardware resources. We propose a novel resource management a...
Optimizing age of information on real-life TCP/IP connections through reinforcement learning Sert, Egemen; Sonmez, Canberk; Baghaee, Sajjad; Uysal, Elif (2018-07-05) Age of Information (AoI) has emerged as a performance metric capturing the freshness of data for status-update based applications ( e.g. , remote monitoring) as a more suitable alternative to classical network performance indicators such as throughput or delay. Optimizing AoI often requires distinctly novel and sometimes counter-intuitive networking policies that adapt the rate of update transmissions to the randomness in network resources. However, almost all previous work on AoI to data has been theoretic...
Optimal photovoltaic size estimation for a campus area considering uncertainties in load, power generation and electricity rates Ali, Syed Muhammad Hassan; Uzgören, Yasemin; Uzgören, Eray; Sustainable Environment and Energy Systems (2015-6) The objective of this thesis is to develop simulation based optimization tools to determine the best strategy for photovoltaic (PV) installations at a campus environment (Middle East Technical University, Northern Cyprus Campus) with consideration of available risks and uncertainties in load, power generation and electricity rates. The first step is to accurately characterize the electricity consumption (load) pattern of the campus. Electricity demand is modeled using different forecasting models based on h...
Photovoltaic power plant design considering multiple uncertainties and risk Merzifonluoglu, Yasemin; Uzgoren, Eray (2018-03-01) The objective of this study was to develop stochastic optimization tools for determining the best strategy of photovoltaic installations in a campus environment with consideration of uncertainties in load, power generation and system performance. In addition to a risk neutral approach, we used Conditional Value-at-Risk to estimate the risk in our problem. The resulting Mixed Integer Programming models were formulated using a scenario-based approach. To minimize the mismatch between supply and demand, hourly...

Citation Formats

E. Balevi and R. D. Gitlin, “Synergies between cloud-fag-thing and brain-spinal cord-nerve networks,” presented at the 2018 Information Theory and Applications Workshop, ITA 2018, California, Amerika Birleşik Devletleri, 2018, Accessed: 00, 2022. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85057265213&origin=inward.